> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Embeddings

> Convert text to vectors for semantic search

Embeddings convert text to vectors for semantic similarity and search.

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
    subgraph "Embeddings"
        T[📝 Text] --> E[🔢 Embedder]
        E --> V[📊 Vector]
        V --> S[🔍 Search]
    end
    
    classDef text fill:#6366F1,stroke:#7C90A0,color:#fff
    classDef vector fill:#10B981,stroke:#7C90A0,color:#fff
    
    class T text
    class E,V,S vector
```

## Quick Start

<Steps>
  <Step title="Create Embeddings">
    ```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    use praisonai::Embedder;

    let embedder = Embedder::new("openai");

    let vector = embedder.embed("Hello world").await?;
    println!("Dimensions: {}", vector.len());
    ```
  </Step>

  <Step title="Use with Knowledge">
    ```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    use praisonai::{Agent, KnowledgeConfig};

    let config = KnowledgeConfig::new()
        .embedder("openai")
        .source("docs/");

    let agent = Agent::new()
        .name("Assistant")
        .knowledge(config)
        .build()?;

    // Knowledge automatically uses embeddings for search
    ```
  </Step>
</Steps>

***

## Embedder Options

| Embedder | Model                  | Dimensions |
| -------- | ---------------------- | ---------- |
| `openai` | text-embedding-3-small | 1536       |
| `cohere` | embed-english-v3       | 1024       |
| `local`  | all-MiniLM-L6-v2       | 384        |

***

## Related

<CardGroup cols={2}>
  <Card title="Knowledge" icon="book" href="/docs/rust/knowledge">
    RAG system
  </Card>

  <Card title="Database" icon="database" href="/docs/rust/database">
    Vector storage
  </Card>
</CardGroup>